Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Seeed-Projects/Seeed-Jetson-DevelopTool --skill deploy-live-vlm-webuigit clone --depth 1 https://github.com/Seeed-Projects/Seeed-Jetson-DevelopToolWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/seeed-projects/seeed-jetson-developtool/deploy-live-vlm-webui)<a href="https://agentmods.dev/skills/seeed-projects/seeed-jetson-developtool/deploy-live-vlm-webui"><img src="https://agentmods.dev/badge/skills/seeed-projects/seeed-jetson-developtool/deploy-live-vlm-webui.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00069 | $0.00769 |
| Opus 5 | $0.00034 | $0.00385 |
| Sonnet 5 | $0.00014 | $0.00154 |
| Haiku 4.5 | $0.00007 | $0.00077 |
Grade D, and why
deploy-live-vlm-webui scanned grade D with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo apt install -y openssl python3-pip Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://ollama.com/install.sh | sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://ollama.com/install.sh | sh How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deploy Live VLM WebUI on reComputer Jetson
Live VLM WebUI streams your webcam to any VLM for live AI-powered visual analysis. This skill installs Ollama + llama3.2-vision and the WebUI on Jetson.
Execution model
Run one phase at a time. After each phase:
- Relay all output to the user.
- If output contains
[STOP]→ stop, consult the failure decision tree. - If output ends with
[OK]→ tell the user "Phase N complete" and proceed.
Prerequisites
| Requirement | Detail |
|---|---|
| Hardware | reComputer Super J4012 (Orin NX 16GB) or similar |
| JetPack | 6.2 |
| Camera | USB camera connected to Type-A port |
| Network | Internet for model download (~7GB) |
Phase 1 — Install and configure Ollama (~10–15 min)
curl -fsSL https://ollama.com/install.sh | sh
ollama pull llama3.2-vision:11b
Verify:
ollama list
# Expected: llama3.2-vision:11b listed
[OK] when model appears in ollama list. [STOP] if download fails or OOM.
Phase 2 — Install Live VLM WebUI (~3 min)
sudo apt install -y openssl python3-pip
python3 -m pip install --user live-vlm-webui
echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.bashrc
source ~/.bashrc
Verify:
which live-vlm-webui
[OK] when the binary path is printed. [STOP] if pip install fails.
Phase 3 — Launch and configure WebUI (~2 min)
live-vlm-webui
Open browser at https://localhost:8090, then configure:
- VLM API Configuration → select
ollamaengine → selectllama3.2-visionmodel - Camera and App Control → select
USB Camera - Click Run to start inference
[OK] when inference results appear in the browser.
Failure decision tree
| Symptom | Action |
|---|---|
| Ollama install fails | Check internet. Retry: curl -fsSL https://ollama.com/install.sh | sh. |
| Model pull OOM or killed | 16GB RAM minimum for 11b model. Free memory by stopping other processes. |
live-vlm-webui: command not found |
Ensure ~/.local/bin is in PATH: source ~/.bashrc. |
| WebUI not accessible at port 8090 | Check firewall: sudo ufw allow 8090. Verify process is running. |
| USB camera not detected in WebUI | Check camera: ls /dev/video*. Replug camera. |
| Inference very slow | Expected on 16GB devices. Consider using a smaller vision model. |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 100 lines · 69 tokens per session scan D 81c88bbb2e03
deploy-live-vlm-webui is a skill published in the GitHub repository Seeed-Projects/Seeed-Jetson-DevelopTool (54 stars, last pushed today), licensed MIT. It adds 69 tokens to every session and 769 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
spark-environment-setup
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.
spark-memory-thermal-ops
Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring temperature and power during multi-hour training.
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
llama-cpp
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
amc-run-rtsp-calibration
Calibrate a new dataset from live RTSP camera streams via the AutoMagicCalib REST API. Use when the user provides RTSP URLs or asks to calibrate live cameras; VIOS records clips, AMC ingests them, then runs calibration.
amc-run-video-calibration
Calibrates pre-recorded cam.mp4 datasets through the AutoMagicCalib REST API. Use for user-supplied local MP4s; route live RTSP streams to amc-run-rtsp-calibration.